CN107809302B - File metadata redundancy transmission and receiving method and system under unreliable link - Google Patents
File metadata redundancy transmission and receiving method and system under unreliable link Download PDFInfo
- Publication number
- CN107809302B CN107809302B CN201710730664.7A CN201710730664A CN107809302B CN 107809302 B CN107809302 B CN 107809302B CN 201710730664 A CN201710730664 A CN 201710730664A CN 107809302 B CN107809302 B CN 107809302B
- Authority
- CN
- China
- Prior art keywords
- data
- redundancy
- file metadata
- file
- erasure code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0078—Avoidance of errors by organising the transmitted data in a format specifically designed to deal with errors, e.g. location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/22—Arrangements for detecting or preventing errors in the information received using redundant apparatus to increase reliability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Communication Control (AREA)
Abstract
The invention discloses a file metadata redundancy transmission and receiving method and system under an unreliable link, which are used for solving the problems of slow response and performance reduction of a file system caused by retransmission of packet loss data in the existing transmission process. The method comprises the following steps: s1, judging whether the sent data is file metadata or not, if not, sending the file data by adopting a TCP (transmission control protocol); if yes, go to step S2; and S2, determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data by adopting a UDP protocol. The invention separates file data and metadata and transmits the file data and the metadata by using different transmission protocols, the metadata uses copy/erasure code redundancy and is transmitted by using a UDP protocol, and if a small amount of packet loss occurs in the transmission process, the client can locally and immediately reconstruct the lost data and is transparent to upper application.
Description
Technical Field
The invention relates to the field of data transmission, in particular to a method and a system for transmitting and receiving file metadata redundancy under an unreliable link.
Background
Compared with a local area network, the cross-region wide area network has the characteristics of small bandwidth, large time delay and large packet loss rate of data packets. Under a long link similar to a link crossing the pacific, the packet loss rate can sometimes reach 3% -5%.
The wide area network based transmission protocols mainly include TCP and UDP. Under TCP, the sender needs to wait for the acknowledgement information of the receiver to determine whether to continue sending or to resend the data after timeout, so that the transmission is reliable but the delay is increased; UDP has no acknowledgement, so there is a risk of data loss but the transmission speed is faster. File transfers almost without exception use TCP to ensure data integrity, but applications that focus more on fluency in real-time audio, video, etc., such as web stations, video conferencing, etc., allow for a small amount of data loss, and therefore UDP can be used.
Data are transmitted by using a reliable transmission protocol on an unreliable link with data packet loss, and time delay can be increased due to overtime waiting and data retransmission when the packet loss occurs, so that the unreliable transmission protocol can be used for transmitting in time delay sensitive application, but the problem of data packet loss is solved.
The patent with publication number CN106130693A provides a reliable transmission method based on UDP, which is a reliable transmission protocol on UDP layer, where the reliable transmission protocol includes reliable transmission, unreliable transmission, and out-of-order transmission; reliable transmission, which is used for providing reliable data transmission between two upper layer applications, wherein the received datagram needs to be confirmed, the lost datagram needs to be retransmitted, and the received datagram is submitted to the upper layer applications according to the sequence of the reliable serial number of the datagram; unreliable transmission, which is used for providing unreliable data transmission between two upper layer applications, the received datagram does not need to be confirmed, the lost datagram does not need to be retransmitted, and the received datagram is submitted to the upper layer applications according to the sequence of the unreliable serial number of the datagram; and the disorder transmission is used for providing disorder data transmission between two upper-layer applications, the received datagram does not need to be confirmed, the lost data does not need to be retransmitted, and the received datagram is directly submitted to the upper-layer applications according to the receiving sequence. The invention has good reliability. The invention is based on UDP, uses acknowledgements and retransmissions to achieve reliable transmission, similar to the TCP transmission strategy, but cannot handle the metadata of the file system separately.
The patent publication CN1339749A provides a local retransmission method using Transmission Control Protocol (TCP) in unreliable transmission network, which can provide reliable delivery of out-of-order TCP packet data on the unreliable transmission link, recover all packets without congestion loss, and avoid unreal window capacity adjustment at the TCP source. And adjusting the transmission sequence of the link layer and the unreal window capacity of the TCP source end. A TCP local retransmission method which adopts the link layer transmission sequence and the transmission sequence of the TCP source end to detect together determines whether a data packet is lost and retransmitted or not by inserting a local sequence number time mark into a TCP data packet and a TCP confirmation packet and jointly judging with a confirmation sequence number AN, and then avoids the false operation of the TCP source end by adopting the clear retransmission ERN feedback. The TCP performance of the wireless network can be greatly improved. The invention uses TCP in unreliable transmission network to ensure data integrity, but causes time delay increase.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method and a system for transmitting and receiving file metadata redundancy under an unreliable link, so as to solve the problems of slow response and performance degradation of a file system caused by retransmission of lost data in the existing transmission process.
In order to achieve the purpose, the invention adopts the technical scheme that:
a method for transmitting file metadata redundancy under an unreliable link comprises the following steps:
s1, judging whether the sent data is file metadata or not, if not, sending the file data by adopting a TCP (transmission control protocol); if yes, go to step S2;
and S2, determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data by adopting a UDP protocol.
Further, step S2 specifically includes:
judging whether the data volume of the file metadata exceeds a preset threshold value, and if not, using copy redundancy; if so, erasure code redundancy is used.
Further, the step of using erasure code redundancy in step S2 specifically includes:
partitioning the data according to a user-configured level of protection (i.e., redundancy);
and calculating check data by adopting a standard erasure code.
A method for receiving file metadata redundancy under an unreliable link comprises the following steps:
SA, judging whether the received data belongs to file metadata or redundant data, and if not, submitting the data upwards; if yes, entering the step SB;
SB, detecting whether the file metadata have packet loss or not, and if not, submitting upwards; if yes, entering step SC;
SC, judge whether the said file metadata can be recovered, if not, use TCP to request the sending end to lose the data; if yes, entering the step SD;
SD, receiving the redundant data and combining the file metadata to recover the lost data;
and SE, submitting the received file metadata and the recovered lost data upwards according to the original sequence and discarding the redundant data.
Further, the step SD specifically includes:
judging whether the redundancy mode is copy redundancy or not, if so, recovering the lost data;
and if the redundancy mode is erasure code redundancy, reconstructing the lost data by adopting the erasure code.
A system for redundant transmission of file metadata over unreliable links, comprising the steps of:
the first judging module is used for judging whether the sent data is file metadata or not, and if not, the file data is sent out by adopting a TCP (transmission control protocol);
and the redundancy mode determining module is used for determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data by adopting a UDP protocol.
Further, the module for determining the redundancy mode specifically includes:
a copy redundancy unit for using copy redundancy when the data amount of the file metadata does not exceed a preset threshold;
and the erasure code redundancy unit is used for using erasure code redundancy when the data quantity of the file metadata exceeds a preset threshold value.
Further, the erasure code redundancy unit is specifically configured to divide the data according to a protection level configured by a user and calculate the check data by using a standard erasure code.
A system for redundant reception of file metadata over an unreliable link, comprising:
the second judgment module is used for judging whether the received data belongs to file metadata or redundant data, and if not, submitting the data upwards;
the detection module is used for detecting whether the file metadata has lost packets or not, and if not, submitting the file metadata upwards;
the third judging module is used for judging whether the file metadata can be recovered, and if not, the third judging module uses TCP to request the sending end for losing data;
the recovery data module is used for receiving the redundant data and recovering the lost data by combining the file metadata;
and the submitting module is used for submitting the received file metadata and the recovered lost data upwards according to an original sequence and discarding the redundant data.
Further, the data recovery module specifically includes:
the duplicate redundancy recovery unit is used for judging whether the redundancy mode is duplicate redundancy or not, and if so, recovering the lost data;
and the erasure code redundancy recovery unit is used for reconstructing the lost data by adopting an erasure code if the redundancy mode is erasure code redundancy.
Compared with the traditional technology, the invention has the following advantages:
the invention uses copy/erasure code redundancy, uses UDP protocol transmission, if part of packet loss occurs in the transmission process, the client can reconstruct lost data locally and instantly and is transparent to upper application.
Drawings
FIG. 1 is a flowchart illustrating a method for transmitting metadata of a file over an unreliable link according to an embodiment;
FIG. 2 is a diagram of a redundant transmission system for file metadata over an unreliable link according to an embodiment;
fig. 3 is a flowchart of a file metadata redundancy transmission method under an unreliable link according to the second embodiment;
FIG. 4 is a diagram of a redundant transmission system for file metadata over an unreliable link according to the second embodiment;
FIG. 5 is a diagram illustrating a packet packing format according to an embodiment;
fig. 6 is a schematic diagram of erasure code redundancy according to an embodiment.
Detailed Description
The following are specific embodiments of the present invention and are further described with reference to the drawings, but the present invention is not limited to these embodiments.
Example one
The embodiment provides a file metadata redundancy transmission method under an unreliable link, as shown in fig. 1, including the steps of:
s11: judging whether the sent data is file metadata or not, and if not, sending the file data by adopting a TCP (transmission control protocol); if yes, go to step S12;
s12: and determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data by adopting a UDP protocol.
Computer users' data is stored and organized in the form of file systems for easy lookup and access. FAT32, NTFS, is a common Windows file system, and the current Linux main file system is ext 4. The network-based file systems mainly include CIFS, NFS, and the like. The file system data is divided into file data and file metadata.
File data refers to the content of the file itself, and file metadata is data describing the file data, such as file name, file size, modification date, access rights, storage location on the disk, and the like. Compared with file data, the data volume of file metadata is very small, and the influence of adding redundancy on the total transmission volume is small. In addition, metadata access by operating systems or computer users is a frequent operation, and can account for over 70% of all file system operations. Therefore, for a network-based file system, optimizing access to metadata is of great significance to improving overall performance of the file system, especially user experience.
In the embodiment, the file metadata is transmitted by using a UDP protocol by using copy/erasure code redundancy, and if part of packet loss occurs in the transmission process, the client can locally and immediately reconstruct the lost data and is transparent to upper-layer application. The problems of slow response and performance reduction of a file system caused by retransmission of packet loss data in the transmission process of file metadata based on TCP in the traditional technology can be reduced or eliminated.
In this embodiment, step S11 first determines whether the sent data is file data or file metadata, and if the sent data is file data, the data is sent out using a TCP protocol.
In this embodiment, step S12 specifically includes:
judging whether the data volume of the file metadata exceeds a preset threshold value, and if not, using copy redundancy; if so, erasure code redundancy is used.
Wherein, the step of using erasure code redundancy specifically includes:
partitioning the data according to a protection level configured by a user;
and calculating check data by adopting a standard erasure code.
Copy, also known as data copy, is a traditional method for protecting data in a mirroring manner, and has been widely used in the field of data storage for decades. The erasure code technology is different from the copy technology in that the erasure code achieves the purpose of data protection with lower storage overhead and higher CPU calculation overhead.
When a sending end sends file metadata, whether copy redundancy or erasure code redundancy is adopted is determined according to the data volume. If all data can be packaged into a UDP data packet, copy redundancy is adopted; if the metadata is large, for example, a directory with a large number of files is browsed, and a plurality of UDP packets are required to be transmitted, erasure code redundancy is adopted. The redundant data package is sent immediately following the file metadata.
Specifically, for example, the data amount is less than one UDP packet, copy redundancy is used, as shown in fig. 5, copies are generated according to the number of copies configured by the user, and the copies are packaged and sent out using the UDP protocol. If the data amount is large, for example, a plurality of UDP packets are reached, erasure code redundancy is used, as shown in fig. 6, according to the protection level configured by the user, data is separated, check data is calculated by using a standard erasure code (for example, Reed-Solomon coding), and the check is packed and sent by using a UDP protocol, and the sending is completed.
In this embodiment, the sending end performs redundancy on the file metadata and transmits the file metadata by using UDP, and the file data is transmitted by using TCP according to a conventional method. If the metadata packet loss occurs in the transmission process, the client can recover the metadata in real time and locally. In addition, since redundancy itself increases network overhead, a method of combining a replica and an erasure code is used to reduce negative effects of redundancy as much as possible.
The embodiment also provides a file metadata redundant transmission system under an unreliable link, as shown in fig. 2, including:
the first judging module 21 is configured to judge whether the sent data is file metadata, and if not, send out the file data by using a TCP protocol;
and a redundancy mode determining module 22, configured to determine a redundancy mode according to the data amount of the file metadata, and send the file metadata and the redundancy data out using a UDP protocol.
In this embodiment, the first determining module 21 first determines whether the sent data is file metadata or file data. If the file data is the file data, the file data is sent out by adopting a TCP protocol. If the file metadata exists, the redundancy mode determining module 22 determines a redundancy mode according to the data volume of the file metadata, and then sends out the file metadata and the redundancy data by using a UDP protocol.
In this embodiment, the module for determining a redundancy mode specifically includes:
the copy redundancy unit is used for using copy redundancy when the data quantity of the file metadata does not exceed a preset threshold;
and the erasure code redundancy unit is used for using erasure code redundancy when the data quantity of the file metadata exceeds a preset threshold value.
The erasure code redundancy unit is specifically configured to divide data according to a protection level configured by a user and calculate check data by using a standard erasure code.
Specifically, when the sending end sends the file metadata, whether copy redundancy or erasure code redundancy is adopted is determined according to the data volume. If all data can be packaged into a UDP data packet, copy redundancy is adopted; if the metadata is large, for example, a directory with a large number of files is browsed, and a plurality of UDP packets are required to be transmitted, erasure code redundancy is adopted. The redundant data package is sent immediately following the file metadata.
Specifically, for example, the data amount is less than one UDP packet, copy redundancy is used, as shown in fig. 5, copies are generated according to the number of copies configured by the user, and the copies are packaged and sent out using the UDP protocol. If the data amount is large, for example, a plurality of UDP packets are reached, erasure code redundancy is used, as shown in fig. 6, the data is divided according to the protection level configured by the user, the check data is calculated by using a standard erasure code (for example, Reed-Solomon coding), and the check is packed and sent by using a UDP protocol, and the transmission is completed.
Example two
The embodiment provides a method for receiving file metadata redundancy under an unreliable link, as shown in fig. 3, including the steps of:
s31: judging whether the received data belongs to file metadata or redundant data, if not, submitting the data upwards; if yes, go to step S32;
s32: detecting whether the file metadata have packet loss or not, and if not, submitting upwards; if yes, go to step S33;
s33: judging whether the file metadata can be recovered, if not, using TCP to request the sending end for losing data; if yes, go to step S34;
s34: receiving redundant data and recovering lost data by combining file metadata;
s35: the received file metadata and the recovered lost data are committed upward in the original order and the redundant data is discarded.
In this embodiment, after receiving the data, the receiving end first determines whether the data belongs to file metadata or redundant data, and if not, the receiving end receives the file data and submits the file data directly upward.
And judging whether packet loss occurs or not and the severity of the packet loss according to the data packet sequence number of the file metadata. If the packet loss is in the recoverable range, namely the packet loss amount is not more than the data protection level, calling a data recovery module, recovering the lost data, and submitting the lost data to an upper layer application in sequence. And if the packet loss is not recoverable, requesting the transmitting end to retransmit. For file data, it is sent in TCP and therefore does not intervene.
Specifically, determining the severity of packet loss, if the number of packet losses is greater than the redundancy, then data loss is unavoidable, and using a TCP to request the sending end for the lost data, otherwise, receiving the redundant data, and combining the received file metadata to recover the lost data.
In this embodiment, step S34 specifically includes:
judging whether the redundancy mode is copy redundancy or not, and if so, recovering the lost data;
and if the redundancy mode is erasure code redundancy, reconstructing the lost data by adopting the erasure code.
Specifically, the redundancy mode of the redundant data is divided into copy redundancy and erasure code redundancy, and if the redundancy mode is copy redundancy, the lost data is directly recovered; if the data is not copy redundancy, the redundancy mode is erasure code redundancy, and the erasure code is adopted to reconstruct the lost data.
Finally, the file metadata and the recovered data are submitted upwards according to the original sequence, and the redundant data are discarded. The reception is completed.
If partial packet loss occurs in the transmission process and the packet loss does not exceed the recoverable range, the lost data can be reconstructed locally and immediately. The delay increase caused by overtime waiting and data retransmission is avoided.
The embodiment also provides a system for receiving file metadata redundancy under an unreliable link, as shown in fig. 4, including:
a second judging module 41, configured to judge whether the received data belongs to file metadata or redundant data, and if not, submit the received data upwards; if yes, go to step S32;
the detection module 42 is configured to detect whether the file metadata has a packet loss, and if not, submit the file metadata upward; if yes, go to step S33;
a third determining module 43, configured to determine whether the file metadata is recoverable, and if not, request the sending end for the missing data by using a TCP; if yes, go to step S34;
a recovery data module 44 for receiving the redundant data and recovering the lost data in combination with the file metadata;
a commit module 45, configured to commit the received file metadata and the recovered lost data upward in the original order and discard the redundant data.
In this embodiment, after the receiving end receives the data, the first determining module 41 first determines whether the data belongs to the file metadata or the redundant data, and if not, the received data is the file data, and the file data is directly submitted upwards.
The detection module 42 determines whether packet loss occurs according to the data packet sequence number of the file metadata, and if not, the data packet is directly submitted upwards. If there is a packet loss, the third determining module 43 determines the severity of the packet loss. And (4) when the added packet loss is in a recoverable range, namely the packet loss quantity is not more than the data protection level, calling a data recovery module, recovering the lost data, and submitting the lost data to an upper layer application in sequence. And if the packet loss is not recoverable, requesting the transmitting end to retransmit. For file data, it is sent in TCP and therefore does not intervene.
In this embodiment, the data recovery module 44 specifically includes:
the duplicate redundancy recovery unit is used for judging whether the redundancy mode is duplicate redundancy or not, and if so, recovering the lost data;
and the erasure code redundancy recovery unit is used for reconstructing the lost data by adopting the erasure code if the redundancy mode is erasure code redundancy.
Specifically, if the redundancy mode is duplicate redundancy, the duplicate redundancy recovery unit directly recovers the lost data; if the data is not copy redundancy, the redundancy mode is erasure code redundancy, and the erasure code redundancy recovery unit reconstructs the lost data by adopting the erasure code.
Finally, the commit module 45 commits the file metadata and the restored data upward in the original order, while discarding the redundant data. The reception is completed.
The method and the system provided by the embodiment can reconstruct lost data locally and instantly under the condition of packet loss within a certain range. The delay increase caused by overtime waiting and data retransmission is avoided, and the user experience is improved.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (9)
1. A method for transmitting file metadata redundantly under an unreliable link is characterized by comprising the following steps:
s1, judging whether the sent data is file metadata or not, if not, sending the file data by adopting a TCP (transmission control protocol); if yes, go to step S2;
s2, determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data out by adopting a UDP protocol; the method specifically comprises the following steps:
judging whether the data volume of the file metadata exceeds a preset threshold value, and if not, using copy redundancy; if so, erasure code redundancy is used.
2. The method for transmitting the file metadata redundancy under the unreliable link according to claim 1, wherein the step of using the erasure code redundancy in step S2 specifically includes:
dividing data according to redundancy configured by a user;
and calculating check data by adopting a standard erasure code.
3. A method for receiving file metadata redundancy under an unreliable link is characterized by comprising the following steps:
SA, judging whether the received data belongs to file metadata or redundant data, and if not, submitting the data upwards; if yes, entering the step SB;
SB, detecting whether the file metadata have packet loss or not, and if not, submitting upwards; if yes, entering step SC;
SC, judge whether the said file metadata can be recovered, if not, use TCP to request the sending end to lose the data; if yes, entering the step SD;
SD, receiving the redundant data and combining the file metadata to recover the lost data; and SE, submitting the received file metadata and the recovered lost data upwards according to the original sequence and discarding the redundant data.
4. The method for receiving the file metadata redundancy under the unreliable link according to claim 3, wherein the step SD specifically includes:
judging whether the redundancy mode is copy redundancy or not, if so, recovering the lost data;
and if the redundancy mode is erasure code redundancy, reconstructing the lost data by adopting the erasure code.
5. A system for redundant transmission of file metadata over unreliable links, comprising the steps of:
the first judging module is used for judging whether the sent data is file metadata or not, and if not, the file data is sent out by adopting a TCP (transmission control protocol);
and the redundancy mode determining module is used for determining a redundancy mode according to the data volume of the file metadata and sending the file metadata and the redundancy data by adopting a UDP protocol.
6. The system according to claim 5, wherein the redundancy mode determining module specifically includes:
a copy redundancy unit for using copy redundancy when the data amount of the file metadata does not exceed a preset threshold;
and the erasure code redundancy unit is used for using erasure code redundancy when the data quantity of the file metadata exceeds a preset threshold value.
7. The system according to claim 6, wherein the erasure code redundancy unit is specifically configured to divide the data according to a redundancy level configured by a user and calculate the check data using a standard erasure code.
8. A system for redundant reception of file metadata over an unreliable link, comprising:
the second judgment module is used for judging whether the received data belongs to file metadata or redundant data, and if not, submitting the data upwards;
the detection module is used for detecting whether the file metadata has lost packets or not, and if not, submitting the file metadata upwards;
the third judging module is used for judging whether the file metadata can be recovered, and if not, the third judging module uses TCP to request the sending end for losing data;
the recovery data module is used for receiving the redundant data and recovering the lost data by combining the file metadata; and the submitting module is used for submitting the received file metadata and the recovered lost data upwards according to an original sequence and discarding the redundant data.
9. The system of claim 8, wherein the recovery data module specifically comprises:
the duplicate redundancy recovery unit is used for judging whether the redundancy mode is duplicate redundancy or not, and if so, recovering the lost data;
and the erasure code redundancy recovery unit is used for reconstructing the lost data by adopting an erasure code if the redundancy mode is erasure code redundancy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710730664.7A CN107809302B (en) | 2017-08-23 | 2017-08-23 | File metadata redundancy transmission and receiving method and system under unreliable link |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710730664.7A CN107809302B (en) | 2017-08-23 | 2017-08-23 | File metadata redundancy transmission and receiving method and system under unreliable link |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107809302A CN107809302A (en) | 2018-03-16 |
| CN107809302B true CN107809302B (en) | 2020-12-15 |
Family
ID=61569772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710730664.7A Active CN107809302B (en) | 2017-08-23 | 2017-08-23 | File metadata redundancy transmission and receiving method and system under unreliable link |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107809302B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109617657B (en) * | 2019-01-22 | 2021-07-30 | 新华三技术有限公司 | Message processing method and device |
| CN109951255A (en) * | 2019-03-27 | 2019-06-28 | 深圳市网心科技有限公司 | A kind of data transmission method based on TCP, system, source device and target device |
| CN113037431A (en) * | 2021-01-28 | 2021-06-25 | 深圳点猫科技有限公司 | Embedded audio data transmission method and system |
| CN113296698A (en) * | 2021-03-29 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Data processing method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917076A (en) * | 2012-11-16 | 2013-02-06 | 网宿科技股份有限公司 | Redundancy encoding-based HTTP (Hyper Text Transport Protocol) message transmission, sending and receiving method |
| CN102937967A (en) * | 2012-10-11 | 2013-02-20 | 南京中兴新软件有限责任公司 | Data redundancy realization method and device |
| CN104836642A (en) * | 2015-04-20 | 2015-08-12 | 哈尔滨工业大学深圳研究生院 | LTP (Licklider Transmission Protocol) optimized design method based on erase code |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5867160B2 (en) * | 2012-02-28 | 2016-02-24 | 富士通株式会社 | COMMUNICATION CONTROL DEVICE, COMMUNICATION CONTROL METHOD, AND COMMUNICATION CONTROL PROGRAM |
-
2017
- 2017-08-23 CN CN201710730664.7A patent/CN107809302B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102937967A (en) * | 2012-10-11 | 2013-02-20 | 南京中兴新软件有限责任公司 | Data redundancy realization method and device |
| CN102917076A (en) * | 2012-11-16 | 2013-02-06 | 网宿科技股份有限公司 | Redundancy encoding-based HTTP (Hyper Text Transport Protocol) message transmission, sending and receiving method |
| CN104836642A (en) * | 2015-04-20 | 2015-08-12 | 哈尔滨工业大学深圳研究生院 | LTP (Licklider Transmission Protocol) optimized design method based on erase code |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107809302A (en) | 2018-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107809302B (en) | File metadata redundancy transmission and receiving method and system under unreliable link | |
| Floyd et al. | An extension to the selective acknowledgement (SACK) option for TCP | |
| Flach et al. | Reducing web latency: the virtue of gentle aggression | |
| Blanton et al. | Using TCP duplicate selective acknowledgement (DSACKs) and stream control transmission protocol (SCTP) duplicate transmission sequence numbers (TSNs) to detect spurious retransmissions | |
| Balakrishnan et al. | Explicit loss notification and wireless web performance | |
| US7213063B2 (en) | Method, apparatus and system for maintaining connections between computers using connection-oriented protocols | |
| US7385923B2 (en) | Method, system and article for improved TCP performance during packet reordering | |
| US8386901B2 (en) | Method, device and software application for transmitting data packets in a communication system | |
| TWI336574B (en) | Error detection and retransmission methods and devices for communication systems | |
| Balan et al. | TCP HACK: TCP header checksum option to improve performance over lossy links | |
| US20090319600A1 (en) | Optimizing program requests over a wide area network | |
| CN106416179A (en) | Transport accelerator implementing extended transmission control functionality | |
| US20090138574A1 (en) | Information processing and transportation architecture for data storage | |
| US8788576B2 (en) | High speed parallel data exchange with receiver side data handling | |
| US20120079076A1 (en) | High speed parallel data exchange | |
| CN110391879B (en) | Packet loss recovery method and device for data transmission network and computer equipment | |
| WO2004030266A1 (en) | Method and devices for error tolerant data transmission, wherein retransmission of erroneous data is performed up to the point where the remaining number of errors is acceptable | |
| WO2019242496A1 (en) | Method and device for data transmission | |
| Chakareski et al. | Computing rate-distortion optimized policies for streaming media to wireless clients | |
| Floyd et al. | RFC2883: An extension to the selective acknowledgement (SACK) option for TCP | |
| US8185795B1 (en) | Side channel for forward error correction used with long-haul IP links | |
| US10461892B2 (en) | Low latency communications | |
| KR100365185B1 (en) | A method and an apparatus for receiving packet data using re-encoding on physical layer to support combine in W-CDMA system | |
| CN102209072A (en) | Method for transmitting deep space file | |
| JP2006352337A (en) | Communication apparatus and communication control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee after: Yinjiang Technology Co.,Ltd. Address before: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee before: ENJOYOR Co.,Ltd. |